© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8974
    Prev
    Next
    INDEX
    Explanations

    temporal references to time

    oai_token-act-pair · gemini-2.0-flash

    non-English terms or technical jargon

    np_token-act-pair-logits · gpt-4o-mini

    passage of time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     five
    -1.33
     six
    -1.31
     ten
    -1.27
     months
    -1.27
     years
    -1.26
     four
    -1.23
     decades
    -1.23
     twenty
    -1.21
     weeks
    -1.20
     seven
    -1.20
    POSITIVE LOGITS
    ंदीखरीदारी
    0.91
     '\\;'
    0.82
    rrggbb
    0.81
    sizeCache
    0.75
    HtmlAttribute
    0.74
    InstanceState
    0.73
    RUnlock
    0.72
    ConstraintMaker
    0.72
    AndroidJUnit
    0.71
     onOptions
    0.69
    Activations Density 0.691%

    No Known Activations